Merge branch 'main' into main

This commit is contained in:
Ian Hildebrand authored and GitHub committed 2026-01-28 11:10:03 -06:00
commit 4c82a8f104
106 files changed
+1336 -287

No files matched your search

+1 -1
View File
@@ -20,5 +20,5 @@ moltbot security audit --deep
moltbot security audit --fix
```
The audit warns when multiple DM senders share the main session and recommends `session.dmScope="per-channel-peer"` for shared inboxes.
The audit warns when multiple DM senders share the main session and recommends `session.dmScope="per-channel-peer"` (or `per-account-channel-peer` for multi-account channels) for shared inboxes.
It also warns when small models (`<=300B`) are used without sandboxing and with web/browser tools enabled.
+4 -3
View File
@@ -130,9 +130,10 @@ Moonshot uses OpenAI-compatible endpoints, so configure it as a custom provider:
- Provider: `moonshot`
- Auth: `MOONSHOT_API_KEY`
- Example model: `moonshot/kimi-k2-0905-preview`
- Example model: `moonshot/kimi-k2.5`
- Kimi K2 model IDs:
{/* moonshot-kimi-k2-model-refs:start */}
- `moonshot/kimi-k2.5`
- `moonshot/kimi-k2-0905-preview`
- `moonshot/kimi-k2-turbo-preview`
- `moonshot/kimi-k2-thinking`
@@ -141,7 +142,7 @@ Moonshot uses OpenAI-compatible endpoints, so configure it as a custom provider:
```json5
{
agents: {
defaults: { model: { primary: "moonshot/kimi-k2-0905-preview" } }
defaults: { model: { primary: "moonshot/kimi-k2.5" } }
},
models: {
mode: "merge",
@@ -150,7 +151,7 @@ Moonshot uses OpenAI-compatible endpoints, so configure it as a custom provider:
baseUrl: "https://api.moonshot.ai/v1",
apiKey: "${MOONSHOT_API_KEY}",
api: "openai-completions",
models: [{ id: "kimi-k2-0905-preview", name: "Kimi K2 0905 Preview" }]
models: [{ id: "kimi-k2.5", name: "Kimi K2.5" }]
}
}
}
+4 -2
View File
@@ -11,7 +11,8 @@ Use `session.dmScope` to control how **direct messages** are grouped:
- `main` (default): all DMs share the main session for continuity.
- `per-peer`: isolate by sender id across channels.
- `per-channel-peer`: isolate by channel + sender (recommended for multi-user inboxes).
Use `session.identityLinks` to map provider-prefixed peer ids to a canonical identity so the same person shares a DM session across channels when using `per-peer` or `per-channel-peer`.
- `per-account-channel-peer`: isolate by account + channel + sender (recommended for multi-account inboxes).
Use `session.identityLinks` to map provider-prefixed peer ids to a canonical identity so the same person shares a DM session across channels when using `per-peer`, `per-channel-peer`, or `per-account-channel-peer`.
## Gateway is the source of truth
All session state is **owned by the gateway** (the “master” Moltbot). UI clients (macOS app, WebChat, etc.) must query the gateway for session lists and token counts instead of reading local files.
@@ -44,6 +45,7 @@ the workspace is writable. See [Memory](/concepts/memory) and
- Multiple phone numbers and channels can map to the same agent main key; they act as transports into one conversation.
- `per-peer`: `agent:<agentId>:dm:<peerId>`.
- `per-channel-peer`: `agent:<agentId>:<channel>:dm:<peerId>`.
- `per-account-channel-peer`: `agent:<agentId>:<channel>:<accountId>:dm:<peerId>` (accountId defaults to `default`).
- If `session.identityLinks` matches a provider-prefixed peer id (for example `telegram:123`), the canonical key replaces `<peerId>` so the same person shares a session across channels.
- Group chats isolate state: `agent:<agentId>:<channel>:group:<id>` (rooms/channels use `agent:<agentId>:<channel>:channel:<id>`).
- Telegram forum topics append `:topic:<threadId>` to the group id for isolation.
@@ -94,7 +96,7 @@ Send these as standalone messages so they register.
{
session: {
scope: "per-sender", // keep group keys separate
dmScope: "main", // DM continuity (set per-channel-peer for shared inboxes)
dmScope: "main", // DM continuity (set per-channel-peer/per-account-channel-peer for shared inboxes)
identityLinks: {
alice: ["telegram:123456789", "discord:987654321012345678"]
},
+7 -6
View File
@@ -2408,8 +2408,8 @@ Use Moonshot's OpenAI-compatible endpoint:
env: { MOONSHOT_API_KEY: "sk-..." },
agents: {
defaults: {
model: { primary: "moonshot/kimi-k2-0905-preview" },
models: { "moonshot/kimi-k2-0905-preview": { alias: "Kimi K2" } }
model: { primary: "moonshot/kimi-k2.5" },
models: { "moonshot/kimi-k2.5": { alias: "Kimi K2.5" } }
}
},
models: {
@@ -2421,8 +2421,8 @@ Use Moonshot's OpenAI-compatible endpoint:
api: "openai-completions",
models: [
{
id: "kimi-k2-0905-preview",
name: "Kimi K2 0905 Preview",
id: "kimi-k2.5",
name: "Kimi K2.5",
reasoning: false,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
@@ -2438,7 +2438,7 @@ Use Moonshot's OpenAI-compatible endpoint:
Notes:
- Set `MOONSHOT_API_KEY` in the environment or use `moltbot onboard --auth-choice moonshot-api-key`.
- Model ref: `moonshot/kimi-k2-0905-preview`.
- Model ref: `moonshot/kimi-k2.5`.
- Use `https://api.moonshot.cn/v1` if you need the China endpoint.
### Kimi Code
@@ -2669,7 +2669,8 @@ Fields:
- `main`: all DMs share the main session for continuity.
- `per-peer`: isolate DMs by sender id across channels.
- `per-channel-peer`: isolate DMs per channel + sender (recommended for multi-user inboxes).
- `identityLinks`: map canonical ids to provider-prefixed peers so the same person shares a DM session across channels when using `per-peer` or `per-channel-peer`.
- `per-account-channel-peer`: isolate DMs per account + channel + sender (recommended for multi-account inboxes).
- `identityLinks`: map canonical ids to provider-prefixed peers so the same person shares a DM session across channels when using `per-peer`, `per-channel-peer`, or `per-account-channel-peer`.
- Example: `alice: ["telegram:123456789", "discord:987654321012345678"]`.
- `reset`: primary reset policy. Defaults to daily resets at 4:00 AM local time on the gateway host.
- `mode`: `daily` or `idle` (default: `daily` when `reset` is present).
+1 -1
View File
@@ -199,7 +199,7 @@ By default, Moltbot routes **all DMs into the main session** so your assistant h
}
```
This prevents cross-user context leakage while keeping group chats isolated. If the same person contacts you on multiple channels, use `session.identityLinks` to collapse those DM sessions into one canonical identity. See [Session Management](/concepts/session) and [Configuration](/gateway/configuration).
This prevents cross-user context leakage while keeping group chats isolated. If you run multiple accounts on the same channel, use `per-account-channel-peer` instead. If the same person contacts you on multiple channels, use `session.identityLinks` to collapse those DM sessions into one canonical identity. See [Session Management](/concepts/session) and [Configuration](/gateway/configuration).
## Allowlists (DM + groups) — terminology
+1 -1
View File
@@ -1026,7 +1026,7 @@ Docs: [Cron jobs](/automation/cron-jobs), [Cron vs Heartbeat](/automation/cron-v
**Can I run Apple macOS only skills from Linux**
Not directly. macOS skills are gated by `metadata.clawdbot.os` plus required binaries, and skills only appear in the system prompt when they are eligible on the **Gateway host**. On Linux, `darwin`-only skills (like `imsg`, `apple-notes`, `apple-reminders`) will not load unless you override the gating.
Not directly. macOS skills are gated by `metadata.moltbot.os` plus required binaries, and skills only appear in the system prompt when they are eligible on the **Gateway host**. On Linux, `darwin`-only skills (like `imsg`, `apple-notes`, `apple-reminders`) will not load unless you override the gating.
You have three supported patterns:
+1 -1
View File
@@ -149,7 +149,7 @@ No configuration needed.
### Metadata Fields
The `metadata.clawdbot` object supports:
The `metadata.moltbot` object supports:
- **`emoji`**: Display emoji for CLI (e.g., `"💾"`)
- **`events`**: Array of events to listen for (e.g., `["command:new", "command:reset"]`)
+59 -121
View File
@@ -7,40 +7,47 @@ read_when:
# exe.dev
Goal: Moltbot Gateway running on an exe.dev VM, reachable from your laptop via:
- **exe.dev HTTPS proxy** (easy, no tunnel) or
- **SSH tunnel** (most secure; loopback-only Gateway)
Goal: Moltbot Gateway running on an exe.dev VM, reachable from your laptop via: `https://<vm-name>.exe.xyz`
This page assumes **Ubuntu/Debian**. If you picked a different distro, map packages accordingly.
If you’re on any other Linux VPS, the same steps apply — you just won’t use the exe.dev proxy commands.
This page assumes exe.dev's default **exeuntu** image. If you picked a different distro, map packages accordingly.
## Beginner quick path
1) Create VM → install Node 22 → install Moltbot
2) Run `moltbot onboard --install-daemon`
3) Tunnel from laptop (`ssh -N -L 18789:127.0.0.1:18789 …`)
4) Open `http://127.0.0.1:18789/` and paste your token
1) [https://exe.new/moltbot](https://exe.new/moltbot)
2) Fill in your auth key/token as needed
3) Click on "Agent" next to your VM, and wait...
4) ???
5) Profit
## What you need
- exe.dev account + `ssh exe.dev` working on your laptop
- SSH keys set up (your laptop → exe.dev)
- Model auth (OAuth or API key) you want to use
- Provider credentials (optional): WhatsApp QR scan, Telegram bot token, Discord bot token, …
- exe.dev account
- `ssh exe.dev` access to [exe.dev](https://exe.dev) virtual machines (optional)
## Automated Install with Shelley
Shelley, [exe.dev](https://exe.dev)'s agent, can install Moltbot instantly with our
prompt. The prompt used is as below:
```
Set up Moltbot (https://docs.molt.bot/install) on this VM. Use the non-interactive and accept-risk flags for moltbot onboarding. Add the supplied auth or token as needed. Configure nginx to forward from the default port 18789 to the root location on the default enabled site config, making sure to enable Websocket support. Pairing is done by "moltbot devices list" and "moltbot device approve <request id>". Make sure the dashboard shows that Moltbot's health is OK. exe.dev handles forwarding from port 8000 to port 80/443 and HTTPS for us, so the final "reachable" should be <vm-name>.exe.xyz, without port specification.
```
## Manual installation
## 1) Create the VM
From your laptop:
From your device:
```bash
ssh exe.dev new --name=moltbot
ssh exe.dev new
```
Then connect:
```bash
ssh moltbot.exe.xyz
ssh <vm-name>.exe.xyz
```
Tip: keep this VM **stateful**. Moltbot stores state under `~/.clawdbot/` and `~/clawd/`.
@@ -52,130 +59,61 @@ sudo apt-get update
sudo apt-get install -y git curl jq ca-certificates openssl
```
### Node 22
Install Node **>= 22.12** (any method is fine). Quick check:
```bash
node -v
```
If you don’t already have Node 22 on the VM, use your preferred Node manager (nvm/mise/asdf) or a distro package source that provides Node 22+.
Common Ubuntu/Debian option (NodeSource):
```bash
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
```
## 3) Install Moltbot
Recommended on servers: npm global install.
Run the Moltbot install script:
```bash
npm i -g moltbot@latest
moltbot --version
curl -fsSL https://molt.bot/install.sh | bash
```
If native deps fail to install (rare; usually `sharp`), add build tools:
## 4) Setup nginx to proxy Moltbot to port 8000
Edit `/etc/nginx/sites-enabled/default` with
```bash
sudo apt-get install -y build-essential python3
```
server {
listen 80 default_server;
listen [::]:80 default_server;
listen 8000;
listen [::]:8000;
## 4) First-time setup (wizard)
server_name _;
Run the onboarding wizard on the VM:
location / {
proxy_pass http://127.0.0.1:18789;
proxy_http_version 1.1;
```bash
moltbot onboard --install-daemon
```
# WebSocket support
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
It can set up:
- `~/clawd` workspace bootstrap
- `~/.clawdbot/moltbot.json` config
- model auth profiles
- model provider config/login
- Linux systemd **user** service (service)
# Standard proxy headers
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
If you’re doing OAuth on a headless VM: do OAuth on a normal machine first, then copy the auth profile to the VM (see [Help](/help)).
## 5) Remote access options
### Option A (recommended): SSH tunnel (loopback-only)
Keep Gateway on loopback (default) and tunnel it from your laptop:
```bash
ssh -N -L 18789:127.0.0.1:18789 moltbot.exe.xyz
```
Open locally:
- `http://127.0.0.1:18789/` (Control UI)
Runbook: [Remote access](/gateway/remote)
### Option B: exe.dev HTTPS proxy (no tunnel)
To let exe.dev proxy traffic to the VM, bind the Gateway to the LAN interface and set a token:
```bash
export CLAWDBOT_GATEWAY_TOKEN="$(openssl rand -hex 32)"
moltbot gateway --bind lan --port 8080 --token "$CLAWDBOT_GATEWAY_TOKEN"
```
For service runs, persist it in `~/.clawdbot/moltbot.json`:
```json5
{
gateway: {
mode: "local",
port: 8080,
bind: "lan",
auth: { mode: "token", token: "YOUR_TOKEN" }
}
# Timeout settings for long-lived connections
proxy_read_timeout 86400s;
proxy_send_timeout 86400s;
}
}
```
Notes:
- Non-loopback binds require `gateway.auth.token` (or `CLAWDBOT_GATEWAY_TOKEN`).
- `gateway.remote.token` is only for remote CLI calls; it does not enable local auth.
## 5) Access Moltbot and grant privileges
Then point exe.dev’s proxy at `8080` (or whatever port you chose) and open your VM’s HTTPS URL:
Access `https://<vm-name>.exe.xyz/?token=YOUR-TOKEN-FROM-TERMINAL`. Approve
devices with `moltbot devices list` and `moltbot device approve`. When in doubt,
use Shelley from your browser!
```bash
ssh exe.dev share port moltbot 8080
```
## Remote Access
Open:
- `https://moltbot.exe.xyz/`
Remote access is handled by [exe.dev](https://exe.dev)'s authentication. By
default, HTTP traffic from port 8000 is forwarded to `https://<vm-name>.exe.xyz`
with email auth.
In the Control UI, paste the token (UI → Settings → token). The UI sends it as `connect.params.auth.token`.
Notes:
- Prefer a **non-default** port (like `8080`) if your proxy expects an app port.
- Treat the token like a password.
Control UI details: [Control UI](/web/control-ui)
## 6) Keep it running (service)
On Linux, Moltbot uses a systemd **user** service. After `--install-daemon`, verify:
```bash
systemctl --user status moltbot-gateway[-<profile>].service
```
If the service dies after logout, enable lingering:
```bash
sudo loginctl enable-linger "$USER"
```
More: [Linux](/platforms/linux)
## 7) Updates
## Updating
```bash
npm i -g moltbot@latest
+1 -1
View File
@@ -185,7 +185,7 @@ cat > /data/moltbot.json << 'EOF'
"bind": "auto"
},
"meta": {
"lastTouchedVersion": "2026.1.26"
"lastTouchedVersion": "2026.1.27-beta.1"
}
}
EOF
+7 -7
View File
@@ -30,17 +30,17 @@ Notes:
# From repo root; set release IDs so Sparkle feed is enabled.
# APP_BUILD must be numeric + monotonic for Sparkle compare.
BUNDLE_ID=bot.molt.mac \
APP_VERSION=2026.1.26 \
APP_VERSION=2026.1.27-beta.1 \
APP_BUILD="$(git rev-list --count HEAD)" \
BUILD_CONFIG=release \
SIGN_IDENTITY="Developer ID Application: <Developer Name> (<TEAMID>)" \
scripts/package-mac-app.sh
# Zip for distribution (includes resource forks for Sparkle delta support)
ditto -c -k --sequesterRsrc --keepParent dist/Moltbot.app dist/Moltbot-2026.1.26.zip
ditto -c -k --sequesterRsrc --keepParent dist/Moltbot.app dist/Moltbot-2026.1.27-beta.1.zip
# Optional: also build a styled DMG for humans (drag to /Applications)
scripts/create-dmg.sh dist/Moltbot.app dist/Moltbot-2026.1.26.dmg
scripts/create-dmg.sh dist/Moltbot.app dist/Moltbot-2026.1.27-beta.1.dmg
# Recommended: build + notarize/staple zip + DMG
# First, create a keychain profile once:
@@ -48,26 +48,26 @@ scripts/create-dmg.sh dist/Moltbot.app dist/Moltbot-2026.1.26.dmg
# --apple-id "<apple-id>" --team-id "<team-id>" --password "<app-specific-password>"
NOTARIZE=1 NOTARYTOOL_PROFILE=moltbot-notary \
BUNDLE_ID=bot.molt.mac \
APP_VERSION=2026.1.26 \
APP_VERSION=2026.1.27-beta.1 \
APP_BUILD="$(git rev-list --count HEAD)" \
BUILD_CONFIG=release \
SIGN_IDENTITY="Developer ID Application: <Developer Name> (<TEAMID>)" \
scripts/package-mac-dist.sh
# Optional: ship dSYM alongside the release
ditto -c -k --keepParent apps/macos/.build/release/Moltbot.app.dSYM dist/Moltbot-2026.1.26.dSYM.zip
ditto -c -k --keepParent apps/macos/.build/release/Moltbot.app.dSYM dist/Moltbot-2026.1.27-beta.1.dSYM.zip
```
## Appcast entry
Use the release note generator so Sparkle renders formatted HTML notes:
```bash
SPARKLE_PRIVATE_KEY_FILE=/path/to/ed25519-private-key scripts/make_appcast.sh dist/Moltbot-2026.1.26.zip https://raw.githubusercontent.com/moltbot/moltbot/main/appcast.xml
SPARKLE_PRIVATE_KEY_FILE=/path/to/ed25519-private-key scripts/make_appcast.sh dist/Moltbot-2026.1.27-beta.1.zip https://raw.githubusercontent.com/moltbot/moltbot/main/appcast.xml
```
Generates HTML release notes from `CHANGELOG.md` (via [`scripts/changelog-to-html.sh`](https://github.com/moltbot/moltbot/blob/main/scripts/changelog-to-html.sh)) and embeds them in the appcast entry.
Commit the updated `appcast.xml` alongside the release assets (zip + dSYM) when publishing.
## Publish & verify
- Upload `Moltbot-2026.1.26.zip` (and `Moltbot-2026.1.26.dSYM.zip`) to the GitHub release for tag `v2026.1.26`.
- Upload `Moltbot-2026.1.27-beta.1.zip` (and `Moltbot-2026.1.27-beta.1.dSYM.zip`) to the GitHub release for tag `v2026.1.27-beta.1`.
- Ensure the raw appcast URL matches the baked feed: `https://raw.githubusercontent.com/moltbot/moltbot/main/appcast.xml`.
- Sanity checks:
- `curl -I https://raw.githubusercontent.com/moltbot/moltbot/main/appcast.xml` returns 200.
+2 -2
View File
@@ -11,10 +11,10 @@ The macOS app surfaces Moltbot skills via the gateway; it does not parse skills
## Data source
- `skills.status` (gateway) returns all skills plus eligibility and missing requirements
(including allowlist blocks for bundled skills).
- Requirements are derived from `metadata.clawdbot.requires` in each `SKILL.md`.
- Requirements are derived from `metadata.moltbot.requires` in each `SKILL.md`.
## Install actions
- `metadata.clawdbot.install` defines install options (brew/node/go/uv).
- `metadata.moltbot.install` defines install options (brew/node/go/uv).
- The app calls `skills.install` to run installers on the gateway host.
- The gateway surfaces only one preferred installer when multiple are provided
(brew when available, otherwise node manager from `skills.install`, default npm).
+13 -2
View File
@@ -9,11 +9,12 @@ read_when:
# Moonshot AI (Kimi)
Moonshot provides the Kimi API with OpenAI-compatible endpoints. Configure the
provider and set the default model to `moonshot/kimi-k2-0905-preview`, or use
provider and set the default model to `moonshot/kimi-k2.5`, or use
Kimi Code with `kimi-code/kimi-for-coding`.
Current Kimi K2 model IDs:
{/* moonshot-kimi-k2-ids:start */}
- `kimi-k2.5`
- `kimi-k2-0905-preview`
- `kimi-k2-turbo-preview`
- `kimi-k2-thinking`
@@ -39,9 +40,10 @@ Note: Moonshot and Kimi Code are separate providers. Keys are not interchangeabl
env: { MOONSHOT_API_KEY: "sk-..." },
agents: {
defaults: {
model: { primary: "moonshot/kimi-k2-0905-preview" },
model: { primary: "moonshot/kimi-k2.5" },
models: {
// moonshot-kimi-k2-aliases:start
"moonshot/kimi-k2.5": { alias: "Kimi K2.5" },
"moonshot/kimi-k2-0905-preview": { alias: "Kimi K2" },
"moonshot/kimi-k2-turbo-preview": { alias: "Kimi K2 Turbo" },
"moonshot/kimi-k2-thinking": { alias: "Kimi K2 Thinking" },
@@ -59,6 +61,15 @@ Note: Moonshot and Kimi Code are separate providers. Keys are not interchangeabl
api: "openai-completions",
models: [
// moonshot-kimi-k2-models:start
{
id: "kimi-k2.5",
name: "Kimi K2.5",
reasoning: false,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 256000,
maxTokens: 8192
},
{
id: "kimi-k2-0905-preview",
name: "Kimi K2 0905 Preview",
+1 -1
View File
@@ -17,7 +17,7 @@ When the operator says “release”, immediately do this preflight (no extra qu
- Use Sparkle keys from `~/Library/CloudStorage/Dropbox/Backup/Sparkle` if needed.
1) **Version & metadata**
- [ ] Bump `package.json` version (e.g., `2026.1.26`).
- [ ] Bump `package.json` version (e.g., `2026.1.27-beta.1`).
- [ ] Run `pnpm plugins:sync` to align extension package versions + changelogs.
- [ ] Update CLI/version strings: [`src/cli/program.ts`](https://github.com/moltbot/moltbot/blob/main/src/cli/program.ts) and the Baileys user agent in [`src/provider-web.ts`](https://github.com/moltbot/moltbot/blob/main/src/provider-web.ts).
- [ ] Confirm package metadata (name, description, repository, keywords, license) and `bin` map points to [`moltbot.mjs`](https://github.com/moltbot/moltbot/blob/main/moltbot.mjs) for `moltbot`.
+1 -1
View File
@@ -60,7 +60,7 @@ Per-skill fields:
## Notes
- Keys under `entries` map to the skill name by default. If a skill defines
`metadata.clawdbot.skillKey`, use that key instead.
`metadata.moltbot.skillKey`, use that key instead.
- Changes to skills are picked up on the next agent turn when the watcher is enabled.
### Sandboxed skills + env vars
+6 -6
View File
@@ -41,7 +41,7 @@ applies: workspace wins, then managed/local, then bundled.
Plugins can ship their own skills by listing `skills` directories in
`moltbot.plugin.json` (paths relative to the plugin root). Plugin skills load
when the plugin is enabled and participate in the normal skill precedence rules.
You can gate them via `metadata.clawdbot.requires.config` on the plugin’s config
You can gate them via `metadata.moltbot.requires.config` on the plugin’s config
entry. See [Plugins](/plugin) for discovery/config and [Tools](/tools) for the
tool surface those skills teach.
@@ -89,7 +89,7 @@ Notes:
- `metadata` should be a **single-line JSON object**.
- Use `{baseDir}` in instructions to reference the skill folder path.
- Optional frontmatter keys:
- `homepage` — URL surfaced as “Website” in the macOS Skills UI (also supported via `metadata.clawdbot.homepage`).
- `homepage` — URL surfaced as “Website” in the macOS Skills UI (also supported via `metadata.moltbot.homepage`).
- `user-invocable` — `true|false` (default: `true`). When `true`, the skill is exposed as a user slash command.
- `disable-model-invocation` — `true|false` (default: `false`). When `true`, the skill is excluded from the model prompt (still available via user invocation).
- `command-dispatch` — `tool` (optional). When set to `tool`, the slash command bypasses the model and dispatches directly to a tool.
@@ -111,7 +111,7 @@ metadata: {"moltbot":{"requires":{"bins":["uv"],"env":["GEMINI_API_KEY"],"config
---
```
Fields under `metadata.clawdbot`:
Fields under `metadata.moltbot`:
- `always: true` — always include the skill (skip other gates).
- `emoji` — optional emoji used by the macOS Skills UI.
- `homepage` — optional URL shown as “Website” in the macOS Skills UI.
@@ -152,7 +152,7 @@ Notes:
- Go installs: if `go` is missing and `brew` is available, the gateway installs Go via Homebrew first and sets `GOBIN` to Homebrew’s `bin` when possible.
- Download installs: `url` (required), `archive` (`tar.gz` | `tar.bz2` | `zip`), `extract` (default: auto when archive detected), `stripComponents`, `targetDir` (default: `~/.clawdbot/tools/<skillKey>`).
If no `metadata.clawdbot` is present, the skill is always eligible (unless
If no `metadata.moltbot` is present, the skill is always eligible (unless
disabled in config or blocked by `skills.allowBundled` for bundled skills).
## Config overrides (`~/.clawdbot/moltbot.json`)
@@ -184,12 +184,12 @@ Bundled/managed skills can be toggled and supplied with env values:
Note: if the skill name contains hyphens, quote the key (JSON5 allows quoted keys).
Config keys match the **skill name** by default. If a skill defines
`metadata.clawdbot.skillKey`, use that key under `skills.entries`.
`metadata.moltbot.skillKey`, use that key under `skills.entries`.
Rules:
- `enabled: false` disables the skill even if it’s bundled/installed.
- `env`: injected **only if** the variable isn’t already set in the process.
- `apiKey`: convenience for skills that declare `metadata.clawdbot.primaryEnv`.
- `apiKey`: convenience for skills that declare `metadata.moltbot.primaryEnv`.
- `config`: optional bag for custom per-skill fields; custom keys must live here.
- `allowBundled`: optional allowlist for **bundled** skills only. If set, only
bundled skills in the list are eligible (managed/workspace skills unaffected).